diff --git a/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/.ipynb_checkpoints/道路通行时间预测-checkpoint.ipynb b/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/.ipynb_checkpoints/道路通行时间预测-checkpoint.ipynb
index af3985e..213c66e 100644
--- a/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/.ipynb_checkpoints/道路通行时间预测-checkpoint.ipynb
+++ b/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/.ipynb_checkpoints/道路通行时间预测-checkpoint.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -18,7 +18,7 @@
     "from scipy.interpolate import UnivariateSpline\n",
     "from sklearn import linear_model\n",
     "import xgboost as xgb\n",
-    "# from ultis import *"
+    "from sklearn.utils import *"
    ]
   },
   {
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -116,7 +116,7 @@
        "4         10.4  "
       ]
      },
-     "execution_count": 6,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -144,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -223,7 +223,7 @@
        "4  4377906284422600514      55     12           1"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -249,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -322,7 +322,7 @@
        "4  4377906284422600514         2          1"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -339,7 +339,8 @@
     "### 任务：预测未来一个月平均通行结果，每两分钟一次\n",
     "回归任务\n",
     "\n",
-    "构建时间序列，基于前几天或者前几十天的数据预测"
+    "构建时间序列，基于前几天或者前几十天的数据预测\n",
+    "https://tianchi.aliyun.com/competition/entrance/231598/information"
    ]
   },
   {
@@ -352,7 +353,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -438,7 +439,7 @@
        "4         10.4  "
       ]
      },
-     "execution_count": 12,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -449,7 +450,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -541,7 +542,7 @@
        "4         10.4 2017-05-06 10:52:00  "
       ]
      },
-     "execution_count": 13,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -563,7 +564,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -580,7 +581,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -594,7 +595,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -673,7 +674,7 @@
        "4  3377906287934510514  2017-05-06     2.251292 2017-05-06 10:52:00"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -686,7 +687,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -696,7 +697,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -713,7 +714,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -792,7 +793,7 @@
        "4  4377906283759500514  2017-05-06     2.140066 2017-05-06 13:24:00"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -811,7 +812,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -890,7 +891,7 @@
        "4  4377906284422600514      55     12           1"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -901,7 +902,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -913,7 +914,7 @@
        "              dtype='datetime64[ns]', freq='2T')"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -925,7 +926,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -992,7 +993,7 @@
        "4  4377906289869500514 2017-03-01 00:08:00"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1007,7 +1008,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -1086,7 +1087,7 @@
        "4  4377906289869500514 2017-03-01 00:08:00  NaN          NaN"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1099,7 +1100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1117,7 +1118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -1196,7 +1197,7 @@
        "184  4377906289869500514 2017-03-01 06:08:00  2017-03-01     2.174752"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1207,7 +1208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1224,7 +1225,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -1316,7 +1317,7 @@
        "184      2.174752  "
       ]
      },
-     "execution_count": 44,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1336,7 +1337,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1361,7 +1362,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -1459,7 +1460,7 @@
        "184      2.174752  2017-03-01-06  "
       ]
      },
-     "execution_count": 46,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1482,7 +1483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -1601,7 +1602,7 @@
        "                    4          NaN           NaN  2017-03-01-06    1.960745  "
       ]
      },
-     "execution_count": 47,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1620,7 +1621,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
@@ -1718,7 +1719,7 @@
        "4           NaN    1.960745  "
       ]
      },
-     "execution_count": 48,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1731,6 +1732,1171 @@
     "df.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "日变化量（分钟）"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def minute_trend(group):\n",
+    "    tmp = group.groupby('hour_minute').mean().reset_index()\n",
+    "    #s的值越小，对数据的拟合越好，但是存在过拟合风险\n",
+    "    spl = UnivariateSpline(tmp.index, tmp['travel_time'].values, s=0.5)\n",
+    "    tmp['minute_trend'] = spl(tmp.index)\n",
+    "    group = pd.merge(group, tmp[['minute_trend', 'hour_minute']], on='hour_minute', how='left')\n",
+    "    return group"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>hour_minute</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-06</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-08</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend hour_minute  \n",
+       "0           NaN    1.960745       06-00  \n",
+       "1           NaN    1.960745       06-02  \n",
+       "2           NaN    1.960745       06-04  \n",
+       "3           NaN    1.960745       06-06  \n",
+       "4           NaN    1.960745       06-08  "
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['hour_minute'] = df.time_interval_begin.map(lambda x: x.strftime('%H-%M'))\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>hour_minute</th>\n",
+       "      <th>minute_trend</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>link_ID</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">3377906280028510514</th>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-00</td>\n",
+       "      <td>-0.252121</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-02</td>\n",
+       "      <td>-0.246743</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-04</td>\n",
+       "      <td>-0.241428</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-06</td>\n",
+       "      <td>-0.236176</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>06-08</td>\n",
+       "      <td>-0.230986</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                   link_ID time_interval_begin        date  \\\n",
+       "link_ID                                                                      \n",
+       "3377906280028510514 0  3377906280028510514 2017-03-01 06:00:00  2017-03-01   \n",
+       "                    1  3377906280028510514 2017-03-01 06:02:00  2017-03-01   \n",
+       "                    2  3377906280028510514 2017-03-01 06:04:00  2017-03-01   \n",
+       "                    3  3377906280028510514 2017-03-01 06:06:00  2017-03-01   \n",
+       "                    4  3377906280028510514 2017-03-01 06:08:00  2017-03-01   \n",
+       "\n",
+       "                       travel_time  travel_time2  date_trend hour_minute  \\\n",
+       "link_ID                                                                    \n",
+       "3377906280028510514 0          NaN           NaN    1.960745       06-00   \n",
+       "                    1          NaN           NaN    1.960745       06-02   \n",
+       "                    2          NaN           NaN    1.960745       06-04   \n",
+       "                    3          NaN           NaN    1.960745       06-06   \n",
+       "                    4          NaN           NaN    1.960745       06-08   \n",
+       "\n",
+       "                       minute_trend  \n",
+       "link_ID                              \n",
+       "3377906280028510514 0     -0.252121  \n",
+       "                    1     -0.246743  \n",
+       "                    2     -0.241428  \n",
+       "                    3     -0.236176  \n",
+       "                    4     -0.230986  "
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df=df.groupby('link_ID').apply(minute_trend)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "与季节残差一样,回归得到的值存在 df['minute_trend']里,因此现在的travel_time再次更新为 df['travel_time]= df['travel_time']-df['minute_trend]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.drop(['hour_minute', 'link_ID'], axis=1)\n",
+    "df = df.reset_index()\n",
+    "df = df.drop('level_1',axis=1)\n",
+    "df['travel_time'] = df['travel_time'] - df['minute_trend']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  \n",
+       "0           NaN    1.960745     -0.252121  \n",
+       "1           NaN    1.960745     -0.246743  \n",
+       "2           NaN    1.960745     -0.241428  \n",
+       "3           NaN    1.960745     -0.236176  \n",
+       "4           NaN    1.960745     -0.230986  "
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "link_infos = pd.read_csv('gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
+    "link_tops = pd.read_csv('gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "基本上大概的走势已经被 date_trend和 hour_trend决定了,剩下就是建模得到这个travel_time如何围绕这两个trends上下变化的\n",
+    "\n",
+    "选择训练特征："
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "      <th>length</th>\n",
+       "      <th>width</th>\n",
+       "      <th>link_num</th>\n",
+       "      <th>area</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  length  width  link_num  area  \n",
+       "0           NaN    1.960745     -0.252121      48      3         2   144  \n",
+       "1           NaN    1.960745     -0.246743      48      3         2   144  \n",
+       "2           NaN    1.960745     -0.241428      48      3         2   144  \n",
+       "3           NaN    1.960745     -0.236176      48      3         2   144  \n",
+       "4           NaN    1.960745     -0.230986      48      3         2   144  "
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "link_infos = pd.merge(link_infos, link_tops, on=['link_ID'], how='left')\n",
+    "link_infos['link_num'] = link_infos['in_links']+link_infos['out_links']\n",
+    "link_infos['area'] = link_infos['length'] * link_infos['width']\n",
+    "df = pd.merge(df, link_infos[['link_ID','length','width', 'link_num', 'area']], on=['link_ID'], how='left')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "      <th>length</th>\n",
+       "      <th>width</th>\n",
+       "      <th>link_num</th>\n",
+       "      <th>area</th>\n",
+       "      <th>vacation</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week_day</th>\n",
+       "      <th>mouth</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  length  width  link_num  area  \\\n",
+       "0           NaN    1.960745     -0.252121      48      3         2   144   \n",
+       "1           NaN    1.960745     -0.246743      48      3         2   144   \n",
+       "2           NaN    1.960745     -0.241428      48      3         2   144   \n",
+       "3           NaN    1.960745     -0.236176      48      3         2   144   \n",
+       "4           NaN    1.960745     -0.230986      48      3         2   144   \n",
+       "\n",
+       "   vacation  minute  hour  day  week_day  mouth  \n",
+       "0       0.0       0     6    1         3      3  \n",
+       "1       0.0       2     6    1         3      3  \n",
+       "2       0.0       4     6    1         3      3  \n",
+       "3       0.0       6     6    1         3      3  \n",
+       "4       0.0       8     6    1         3      3  "
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#时间相关特征\n",
+    "df.loc[df['date'].isin(['2017-04-02','2017-04-03','2017-04-04','2017-04-29','2017-04-30',\n",
+    "                       '2017-05-01','2017-05-28','2017-05-29','2017-05-30']),'vacation']=1\n",
+    "\n",
+    "df.loc[~df['date'].isin(['2017-04-02','2017-04-03','2017-04-04','2017-04-29','2017-04-30',\n",
+    "                       '2017-05-01','2017-05-28','2017-05-29','2017-05-30']),'vacation']=0\n",
+    "\n",
+    "df['minute'] = df['time_interval_begin'].dt.minute\n",
+    "df['hour'] = df['time_interval_begin'].dt.hour\n",
+    "df['day'] = df['time_interval_begin'].dt.day\n",
+    "df['week_day'] = df['time_interval_begin'].map(lambda x: x.weekday() + 1)\n",
+    "df['mouth'] = df['time_interval_begin'].dt.month\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def mean_time(group):\n",
+    "    group['link_ID_en'] = group['travel_time'].mean()\n",
+    "    return group"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "      <th>length</th>\n",
+       "      <th>width</th>\n",
+       "      <th>link_num</th>\n",
+       "      <th>area</th>\n",
+       "      <th>vacation</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week_day</th>\n",
+       "      <th>mouth</th>\n",
+       "      <th>link_ID_en</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000138</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  length  width  link_num  area  \\\n",
+       "0           NaN    1.960745     -0.252121      48      3         2   144   \n",
+       "1           NaN    1.960745     -0.246743      48      3         2   144   \n",
+       "2           NaN    1.960745     -0.241428      48      3         2   144   \n",
+       "3           NaN    1.960745     -0.236176      48      3         2   144   \n",
+       "4           NaN    1.960745     -0.230986      48      3         2   144   \n",
+       "\n",
+       "   vacation  minute  hour  day  week_day  mouth  link_ID_en  \n",
+       "0       0.0       0     6    1         3      3    0.000138  \n",
+       "1       0.0       2     6    1         3      3    0.000138  \n",
+       "2       0.0       4     6    1         3      3    0.000138  \n",
+       "3       0.0       6     6    1         3      3    0.000138  \n",
+       "4       0.0       8     6    1         3      3    0.000138  "
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.groupby('link_ID').apply(mean_time)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "      <th>length</th>\n",
+       "      <th>width</th>\n",
+       "      <th>link_num</th>\n",
+       "      <th>area</th>\n",
+       "      <th>vacation</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week_day</th>\n",
+       "      <th>mouth</th>\n",
+       "      <th>link_ID_en</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  length  width  link_num  area  \\\n",
+       "0           NaN    1.960745     -0.252121      48      3         2   144   \n",
+       "1           NaN    1.960745     -0.246743      48      3         2   144   \n",
+       "2           NaN    1.960745     -0.241428      48      3         2   144   \n",
+       "3           NaN    1.960745     -0.236176      48      3         2   144   \n",
+       "4           NaN    1.960745     -0.230986      48      3         2   144   \n",
+       "\n",
+       "   vacation  minute  hour  day  week_day  mouth  link_ID_en  \n",
+       "0       0.0       0     6    1         3      3          75  \n",
+       "1       0.0       2     6    1         3      3          75  \n",
+       "2       0.0       4     6    1         3      3          75  \n",
+       "3       0.0       6     6    1         3      3          75  \n",
+       "4       0.0       8     6    1         3      3          75  "
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 通行时间长的编号大\n",
+    "sorted_link = np.sort(df['link_ID_en'].unique())\n",
+    "df['link_ID_en'] = df['link_ID_en'].map(lambda x: np.argmin(x >= sorted_link))\n",
+    "df.head()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
diff --git a/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/道路通行时间预测.ipynb b/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/道路通行时间预测.ipynb
index 9cafb82..213c66e 100644
--- a/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/道路通行时间预测.ipynb
+++ b/机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/道路通行时间预测.ipynb
@@ -2708,9 +2708,188 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 44,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>link_ID</th>\n",
+       "      <th>time_interval_begin</th>\n",
+       "      <th>date</th>\n",
+       "      <th>travel_time</th>\n",
+       "      <th>travel_time2</th>\n",
+       "      <th>date_trend</th>\n",
+       "      <th>minute_trend</th>\n",
+       "      <th>length</th>\n",
+       "      <th>width</th>\n",
+       "      <th>link_num</th>\n",
+       "      <th>area</th>\n",
+       "      <th>vacation</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week_day</th>\n",
+       "      <th>mouth</th>\n",
+       "      <th>link_ID_en</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:00:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.252121</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:02:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.246743</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:04:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.241428</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:06:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.236176</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3377906280028510514</td>\n",
+       "      <td>2017-03-01 06:08:00</td>\n",
+       "      <td>2017-03-01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.960745</td>\n",
+       "      <td>-0.230986</td>\n",
+       "      <td>48</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>144</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               link_ID time_interval_begin        date  travel_time  \\\n",
+       "0  3377906280028510514 2017-03-01 06:00:00  2017-03-01          NaN   \n",
+       "1  3377906280028510514 2017-03-01 06:02:00  2017-03-01          NaN   \n",
+       "2  3377906280028510514 2017-03-01 06:04:00  2017-03-01          NaN   \n",
+       "3  3377906280028510514 2017-03-01 06:06:00  2017-03-01          NaN   \n",
+       "4  3377906280028510514 2017-03-01 06:08:00  2017-03-01          NaN   \n",
+       "\n",
+       "   travel_time2  date_trend  minute_trend  length  width  link_num  area  \\\n",
+       "0           NaN    1.960745     -0.252121      48      3         2   144   \n",
+       "1           NaN    1.960745     -0.246743      48      3         2   144   \n",
+       "2           NaN    1.960745     -0.241428      48      3         2   144   \n",
+       "3           NaN    1.960745     -0.236176      48      3         2   144   \n",
+       "4           NaN    1.960745     -0.230986      48      3         2   144   \n",
+       "\n",
+       "   vacation  minute  hour  day  week_day  mouth  link_ID_en  \n",
+       "0       0.0       0     6    1         3      3          75  \n",
+       "1       0.0       2     6    1         3      3          75  \n",
+       "2       0.0       4     6    1         3      3          75  \n",
+       "3       0.0       6     6    1         3      3          75  \n",
+       "4       0.0       8     6    1         3      3          75  "
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# 通行时间长的编号大\n",
     "sorted_link = np.sort(df['link_ID_en'].unique())\n",